# US 10,483,004 B2 · Model-based teeth reconstruction

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,483,004 B2
- Document ID: US10483004B2
- Status: Granted
- Kind: B2
- Application number: 15/280,919
- Filed: 2016-09-29
- Published: 2018-03-29
- Granted: 2019-11-19
- Earliest claimed: 2016-09-29
- Assignees: Disney Enterprises, Inc.; ETH Zürich (Eidgenössische Technische Hochschule Zürich)
- Applicants: Disney Enterprises, Inc.
- Inventors: Chenglei Wu; Derek Bradley; Thabo Beeler; Markus Gross
- Web page: https://patentgrep.com/patent/US10483004B2

## CPC

- G16H 50/50: for simulation or modelling of medical disorders
- A61C 13/0004: {Computer-assisted sizing or machining of dental prostheses}
- G16H 70/20: relating to practices or guidelines
- G16H 70/60: relating to pathologies
- A61D 5/00: Instruments for treating animals' teeth
- G06N 20/00: Machine learning
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61C: DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE (non-driven toothbrushes A46B; {tongue scrapers A61B17/24;} preparations for dentistry A61K6/00; preparations for cleaning the teeth or mouth A61K8/00, A61Q11/00)
- A61D: VETERINARY INSTRUMENTS, IMPLEMENTS, TOOLS, OR METHODS
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system and method for non-invasive reconstruction of an entire object-specific or person-specific teeth row from just a set of photographs of the mouth region of an object (e.g., an animal) or a person (e.g., an actor or a patient) are provided. A teeth statistic model defining individual teeth in a teeth row can be developed. The teeth statistical model can jointly describe shape and pose variations per tooth, and as well as placement of the individual teeth in the teeth row. In some embodiments, the teeth statistic model can be trained using teeth information from 3D scan data of different sample subjects. The 3D scan data can be used to establish a database of teeth of various shapes and poses. Geometry information regarding the individual teeth can be extracted from the 3D scan data. The teeth statistic model can be trained using the geometry information regarding the individual teeth.

## Claims

### Claim 1

A method for reconstructing a three-dimensional (3D) model of teeth of an object from one or more images of the object, the method being performed by a computer system and comprising:
receiving, by the computer system, sample data of teeth rows of different sample subjects;
receiving, by the computer system, tooth templates comprising individual template teeth;
mapping, by the computer system, individual teeth in the teeth rows of the different sample subjects to the individual template teeth;
for each of the individual template teeth, obtaining, by the computer system, a teeth statistical model, the statistical model encoding a deviation in shape and pose for each of the individual template teeth, wherein the teeth statistical model includes information regarding a rigid transformation and an anisotropic scaling factor for the teeth rows, the anisotropic scaling factor comprising different properties depending on a direction of measurement for the teeth rows;
training, by the computer system, each teeth statistical model using the sample data of the teeth rows of the different sample subjects based on the mapping between the individual teeth in the teeth rows of the different sample subjects and the individual template teeth, wherein the training comprises: evaluating the teeth statistics model to provide an instance of a teeth row that represents either an upper or a lower teeth for a sample subject;
acquiring, by the computer system, teeth information from the one or more images of the object; and
reconstructing, by the computer system, a 3D model of teeth of the object by fitting parameters of the trained teeth statistical model to the teeth information acquired from the one or more images of the object.

### Claim 2 (depends on 1)

The method of claim 1, wherein the teeth statistical model encodes an average shape of the tooth, an average pose of the tooth, deviation in shape and pose for the tooth across the different sample subjects, and placement of the tooth in a generic teeth row.

### Claim 3 (depends on 1)

The method of claim 1, wherein the received sample data of the teeth rows of the different sample subjects are 3D scans of a mouth region of the different sample subjects.

### Claim 4 (depends on 1)

The method of claim 1, wherein training the teeth statistical model comprises
performing a principal component analysis to determine a variation in shape for each tooth template.

### Claim 5 (depends on 1)

The method of claim 1, wherein mapping individual teeth in the teeth rows of the different sample subject to the individual template teeth includes receiving an indication of a segmentation contour for the individual teeth, the segmentation contour indicating separation of each of the individual teeth and separation of the teeth and a gum region.

### Claim 6 (depends on 5)

The method of claim 5, wherein the indication further includes marks representing one or more land marks on the individual template teeth.

### Claim 7 (depends on 5)

The method of claim 5, further comprising computing segmentation contour for each tooth based on the received indication.

### Claim 8 (depends on 1)

The method of claim 1, wherein a teeth statistical model is obtained for each type of teeth in the teeth row.

### Claim 9

A system for reconstructing a three-dimensional (3D) model of teeth of an object from one or more images of the object, wherein the system comprises one or more processors configured to execute machine-readable instructions such that when the machine-readable instructions are executed by the one or more processors, the one or more processors are caused to perform:
receiving sample data of teeth rows of different sample subjects;
receiving tooth templates comprising individual template teeth;
mapping individual teeth in the teeth rows of the different sample subject to the individual template teeth;
for each of the individual template teeth, obtaining a teeth statistical model, the statistical model encoding a deviation in shape and pose for each of the individual template teeth, wherein the teeth statistical model includes information regarding a rigid transformation and an anisotropic scaling factor for the teeth rows, the anisotropic scaling factor comprising different properties depending on a direction of measurement for the teeth rows;
training each teeth statistical model using the sample data of the teeth rows of the different sample subjects based on the mapping between the individual teeth in the teeth rows of the different sample subjects and the individual template teeth, wherein the training comprises: evaluating the teeth statistics model to provide an instance of a teeth row that represents either upper or lower teeth for a sample subject;
acquiring teeth information from the one or more images of the object; and
reconstructing a 3D model of teeth of the object by fitting parameters of the trained statistical model to the teeth information acquired from the one or more images of the object.

### Claim 10 (depends on 9)

The system of claim 9, wherein the teeth statistical model encodes an average shape of the tooth, an average pose of the tooth, deviation in shape and pose for the tooth across the subjects, and placement of the tooth in a generic teeth row.

### Claim 11 (depends on 9)

The system of claim 9, wherein the received sample data of the teeth rows of the different sample subjects are 3D scans of a mouth region of the different sample subjects.

### Claim 12 (depends on 9)

The system of claim 9, wherein training the teeth statistical model comprises
performing a principal component analysis to determine a variation in shape for each tooth template.

### Claim 13 (depends on 9)

The system of claim 9, wherein mapping individual teeth in the teeth rows of the different sample subject to the individual template teeth includes receiving an indication of a segmentation contour for the individual teeth, the segmentation contour indicating separation of each of the individual teeth and separation of the teeth and a gum region.

### Claim 14 (depends on 13)

The system of claim 13, wherein the indication further includes marks representing one or more land marks on the individual template teeth.

### Claim 15 (depends on 13)

The system of claim 13, further comprising computing segmentation contour for each tooth based on the received indication.

### Claim 16 (depends on 9)

The system of claim 9, wherein a teeth statistical model is obtained for each type of teeth in the teeth row.